• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.228-229
• /
• 2020

최근 딥러닝 기술은 여러 컴퓨터 비전 응용 분야에서 많이 쓰이고 있다. 물체 인식, 분류 및 영상 생성 등을 예로 들 수 있다. 특히 초고해상도 변환 문제에서 최근 딥러닝을 사용하면서 큰 성능 개선을 얻고 있다. Fast super-resolution convolutional neural network (FSRCNN)은 딥러닝 기반 초고해상도 알고리즘으로 잘 알려져 있으며, 여러 개의 convolutional layer로 추출한 저 해상도의 입력 특징을 활용하여 deconvolutional layer에서 초고해상도의 영상을 출력하는 알고리즘이다. 본 논문에서는 병렬 연산 효율성을 고려한 FPGA 기반 convolutional neural networks 가속기를 제안한다. 특히 deconvolutional layer를 convolutional layer로 변환하는 방법을 통해서 에너지 효율적인 가속기를 설계했다. 또한 제안한 방법은 FPGA 리소스를 고려하여 FSRCNN의 구조를 변형한 Optimal-FSRCNN을 제안한다. 사용하는 곱셈기의 개수를 FSRCNN 대비 2.4 배 압축하였고, 초고해상도 변환 성능을 평가하는 지표인 PSNR은 FSRCNN과 비슷한 성능을 내고 있다. 이를 통해서 FPGA 에 최적화된 네트워크를 구현하여 FHD 입력 영상을 UHD 영상으로 출력하는 실시간 영상처리 기술을 개발했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.800-802
• /
• 2022

최근 성인들을 위한 '키덜트 장난감'의 관심도가 증가하고 있다. 그중 높은 매출을 보이는 RC 카와 VR 의 콘텐츠 부족 및 대중화 문제를 해결하면 시장규모를 성장시킬 수 있다고 판단한다. 본 논문은 차별화된 RC 카 레이싱 게임 개발을 목표로 한다. 스마트폰용 VR 기기를 착용해 영상을 보며 컨트롤러로 RC 카를 조종한다. 또한 실시간 객체 검출이 가능한 YOLOv5 를 활용해 표지판 인식 및 바운딩 박스, 표지판 라벨, 라벨 음성 출력 기능과 오픈 소스 기반 실시간 컴퓨터 비전인 OpenCV 기반 알고리즘을 활용하여 차선을 인식해 이를 기반으로 영상 처리를 거쳐 가상 차선 및 가상 트랙을 출력한다. 결론적으로 RC 카와 VR 로 구현하여 이를 통해 부족한 VR 컨텐츠를 추가하고 접근성을 강화한다.

• The Journal of Korean Association of Computer Education
• /
• v.23 no.2
• /
• pp.41-51
• /
• 2020

The goal of this study is to test the hypothesis that the practicality of EXCEL VBA will be beneficial for SW education for SW non-majors. To this end, we planned the education for non-majors using the EXCEL VBA and conducted 15 weeks of education. According to a follow-up survey conducted after the 15-week education period, 72.21% of the survey respondents said EXCEL was practical. Also, learners who were aware of the necessity of SW education and the importance of SW competence recognized that the computational thinking education using EXCEL VBA had a positive effect on the improvement of computer-related knowledge and experience. Also, learners recognized that learning with EXCEL was easy, while learning with VBA was difficult. The learning process using VBA needs to be composed of project-oriented educational contents that can give a sense of achievement to learners rather than programming-oriented education. And continuous research on project-based learning is needed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.8
• /
• pp.1805-1810
• /
• 2015

Increasing of depth data accessibility, depth data is used in many researches. Motion recognition of computer vision also widely use depth image. More accuracy motion recognition system needs more stable depth data. But depth sensor has a noise. This noise affect accuracy of the motion recognition system, we should noise suppression. In this paper, we propose using spatial domain and temporal domain stabilization for depth image and makes it hardware IP. We adapted our hardware to floor removing algorithm and verification its effect. we did realtime verification using FPGA and APU. Designed hardware has maximum frequency 202.184MHz.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.317-319
• /
• 2021

In Korea, an intelligent transportation system(ITS) is established to efficiently operate traffic congestion on roads and is being used for traffic information collection and speed control systems. Currently, designated and dedicated lanes are in place to ensure traffic circulation and traffic safety, and systematic and accurate illegal vehicle crackdown systems with artificial intelligence technology are needed. In this study, we propose a vehicle number recognition model that can improve the efficiency of the traffic of designated vehicles. By applying computer vision technology, we are going to identify three-lane and four-lane multi-lane roads in real time and detect vehicle numbers by car to suggest ways to crack down on vehicles that violate the designated lane system.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.41 no.4
• /
• pp.39-43
• /
• 2004

A typical theme of active vision systems is gaze-fixing of a camera. Here gaze-fixing of a camera means by steering orientation of a camera so that a given point on the object is always at the center of the image. For this we need to combine a function to analyze image data and a function to control orientation of a camera. This paper presents an algorithm for gaze-fixing of a camera where image analysis and orientation control are designed in a frame. At this time, for avoiding difficulties in implementing and aiming for real-time applications we design the algorithm to be a simple closed-form without using my information related to calibration of the camera or structure estimation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.149-152
• /
• 2007

비전 연구에 있어서 객체 추적은 무엇보다도 중요시 되어 왔다. 특히 비디오 감시 시스템에서의 객체 추적은 매우 중요하다. 본 논문에서는 영상 내에서 움직이는 객체를 추출하고 객체내의 다중 후보블록의 통계적 특징을 이용한 추적 시스템을 구성하였다. 객체를 추적하기 위해서는 먼저 움직이는 객체 추출이 선행되어야 한다. 객체 추출은 영상 내에서 배경 프레임과 매 프레임에서의 현재 프레임간의 차 연산에 의한 가중치를 이용하여 객체의 움직임을 판단하고 추출하였다. 움직이는 객체는 본 논문에서 제안한 다중 후보 블록 알고리즘을 수행하여 추적에 필요한 통계 값을 획득한다. 통계 값으로는 방향성에 필요한 블록의 중심 좌표 값과 객체추적에 필요한 객체간의 매칭 정도를 사용하였다. 본 논문에서 제안한 추적 시스템은 민감한 빛의 변화에도 강건하였으며, 특정 블록에 대해서만 연산 수행을 수행하므로 컴퓨터의 연산을 줄여 실시간 추적도 가능하다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.114-123
• /
• 2023

With the development of computer vision technology, video sensors such as CCTV are detecting incident. However, most of the current incident have been detected based on existing fixed imaging equipment. Accordingly, there has been a limit to the detection of incident in shaded areas where the image range of fixed equipment is not reached. With the recent development of edge-computing technology, real-time analysis of mobile image information has become possible. The purpose of this study is to evaluate the possibility of detecting expressway emergencies by introducing computer vision technology to dash cam. To this end, annotation data was constructed based on 4,388 dash cam still frame data collected by the Korea Expressway Corporation and analyzed using the YOLO algorithm. As a result of the analysis, the prediction accuracy of all objects was over 70%, and the precision of traffic accidents was about 85%. In addition, in the case of mAP(mean Average Precision), it was 0.769, and when looking at AP(Average Precision) for each object, traffic accidents were the highest at 0.904, and debris were the lowest at 0.629.

• Journal of Korea Game Society
• /
• v.14 no.5
• /
• pp.79-86
• /
• 2014

There have been many trials for development of games using augmented reality. This paper presents a 2D puzzle game system using HSV color space to detect hand posture from an input image by smart device's cameras in real time. The developed game in this paper brings smart devices and the computer vision closer. Also this game can be a new interactive technology utilizing both the mobility of smart devices and the tangible interactivity of virtual reality in education and entertainment environments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.6
• /
• pp.1160-1166
• /
• 2006

The information of vehicle is very important for maintaining traffic order under the present complex traffic environments. This paper proposes a new vehicle plate recognition mechanism that is essential to know the information of vehicle. The proposed method uses SVM which is excellent object classification compare to other methods. Two-class SVM is used to find the location of vehicle plate and multi-class SVM is used to recognize the characters in the plate. As a real-time processing system using multi-step image processing and recognition process this method recognizes several different vehicle plates. Through the experimental results of real environmental image and recognition using the proposed method, the performance is proven.